• Home
    • Technology
    • Gaming
    • Entertainment
    • World & Business
    • Science
    • Sports
    • AI
    HomeTechnologyGamingEntertainmentWorld & BusinessScienceSportsAI
    AI
    Reaction

    NXDirection's data labels are claimed to reduce attack success in two tests

    A post says NXDirection labels content as data, with attack success dropping from 38.1% to 0.1% in one test.

    1 Source, 1h ago, first seen 1h ago

    TLDR

    A post praises NXDirection's approach to separating data from instructions for AI agents. It reports attack success falling from 38.1% to 0.1% in one standard test and from 28.4% to 3.7% in a more complex test. The author cautions that the approach does not solve agent security on its own.

    Combined views

    —

    1 Source, first seen 1h ago

    — likes— comments— saves— reposts

    Combined views

    —

    1 Source, first seen 1h ago

    — likes— comments— saves— reposts
    Image: @LeonDerczynski on X

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    Featured Source

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    1 Source

    Leon Derczynski ⚒️☁️🏔️🌲@LeonDerczynskiSeparate control & data plane for agents! This explicit marker affords a nice workaround for the risk presented when data (instead of instructions) are executed. Making that mistake is a classic weakness going way back before modern LLMs - even before Schmidhuber! NXDirection labels content as data rather than instruction-bearing, and using this systems yields a massive drop in attack success from 38.1% to 0.1% in one standard test, and from 28.4% to 3.7% in a more complex and advanced test. That's enormous. This doesn't solve security of agents, but that security is never solved on just one layer alone. What NXDirection presents is a massive advance in the ability to control instruction vs. data separation by LLM-driven code - working exactly at the most problematic layer.1h
    • Home
    • Technology
    • Gaming
    • Entertainment
    • World & Business
    • Science
    • Sports
    • AI

    1 Source

    Leon Derczynski ⚒️☁️🏔️🌲@LeonDerczynskiSeparate control & data plane for agents! This explicit marker affords a nice workaround for the risk presented when data (instead of instructions) are executed. Making that mistake is a classic weakness going way back before modern LLMs - even before Schmidhuber! NXDirection labels content as data rather than instruction-bearing, and using this systems yields a massive drop in attack success from 38.1% to 0.1% in one standard test, and from 28.4% to 3.7% in a more complex and advanced test. That's enormous. This doesn't solve security of agents, but that security is never solved on just one layer alone. What NXDirection presents is a massive advance in the ability to control instruction vs. data separation by LLM-driven code - working exactly at the most problematic layer.1h
    Today's Rank

    —

    Not ranked yet

    Today's Rank

    —

    Not ranked yet